import gradio as gr
import os
import pickle
import numpy as np
from surprise import SVDpp
from sklearn.metrics.pairwise import cosine_similarity

# --- Download Model from Kaggle ---
def download_kaggle_model():
    kaggle_username = os.environ.get("KAGGLE_USERNAME")
    kaggle_key = os.environ.get("KAGGLE_KEY")
    if not kaggle_username or not kaggle_key:
        raise ValueError("Set KAGGLE_USERNAME and KAGGLE_KEY as HF secrets!")

    os.system("mkdir -p ~/.kaggle")
    with open("/root/.kaggle/kaggle.json", "w") as f:
        f.write(f'{{"username":"{kaggle_username}","key":"{kaggle_key}"}}')
    os.chmod("/root/.kaggle/kaggle.json", 0o600)

    # Download your Kaggle model
    print("📥 Downloading model from Kaggle...")
    os.system("kaggle datasets download -d <your-username>/<your-model-dataset> -p ./model --unzip")

# --- Load Models ---
def load_models():
    with open("./model/svdpp_model.pkl", "rb") as f:
        svdpp_model = pickle.load(f)

    with open("./model/content_features.pkl", "rb") as f:
        content_features = pickle.load(f)

    with open("./model/mappings.pkl", "rb") as f:
        mappings = pickle.load(f)

    return svdpp_model, content_features, mappings

# --- Hybrid Prediction ---
def hybrid_predict(user_id, book_id, alpha=0.7):
    try:
        uid = user_encoder.transform([user_id])[0]
        iid = item_encoder.transform([book_id])[0]
    except:
        return "Unknown user_id or book_id"

    svd_pred = svdpp_model.predict(uid, iid).est

    user_liked = np.where(svdpp_model.trainset.ur[uid])[0]
    if len(user_liked) == 0:
        content_score = 0
    else:
        similarities = cosine_similarity(content_features[iid], content_features[user_liked])
        content_score = np.mean(similarities)

    hybrid_score = alpha * svd_pred + (1 - alpha) * content_score * 5
    return round(hybrid_score, 2)

# --- Gradio Interface ---
def recommend(user_id, book_id, alpha=0.7):
    return f"Predicted Rating: {hybrid_predict(user_id, book_id, alpha)}"

# Download model from Kaggle and load
download_kaggle_model()
svdpp_model, content_features, mappings = load_models()
user_encoder = mappings["user_encoder"]
item_encoder = mappings["item_encoder"]

# Start Gradio app
demo = gr.Interface(
    fn=recommend,
    inputs=[
        gr.Textbox(label="User ID"),
        gr.Textbox(label="Book ID"),
        gr.Slider(0, 1, value=0.7, step=0.1, label="Hybrid Weight (alpha)")
    ],
    outputs="text",
    title="📚 Hybrid Book Recommender",
    description="Enter a user_id and book_id to get a predicted rating using a Hybrid SVD++ and Content-based model."
)

demo.launch()